ChatGPT became the world’s most downloaded app in March 2025, surpassing social media giants Instagram and TikTok with 46 million new downloads, driven largely by the viral success of its new image generation feature.
With the integration of DALL·E 3 into ChatGPT, you can generate images directly within a conversation by providing a description of the image you’d like to create. I tried this out by asking for an image of a Series III Land Rover.
At first glance I thought this was a photograph but then I spotted some mistakes, which ChatGPT caught as well:
While it looks pretty convincing at a glance, there are a few telltale signs it’s not a real Series III Land Rover:
- Badge: It says “LAMIS ROVER” instead of “LAND ROVER”—a classic AI hiccup with text.
- Proportions: The front end is a bit off. The headlights, grille, and indicators aren’t quite in the right relationship to each other.
- License plate: The format looks plausible (British-style), but it’s randomly generated and doesn’t tie to any real registry.
- Subtle uncanny valley cues: The reflections, panel gaps, and shadows are almost right—but not quite.
She then asked if I’d like to see the Rover next to my pick-up truck. Sure, why not?
While the photorealism is pretty impressive, the buzz seems to be about “Studio Ghibli-style visuals” which refers to the distinctive look and feel of the animated films produced by Studio Ghibli, the iconic Japanese animation studio co-founded by Hayao Miyazaki. “The visual equivalent of a warm, slightly surreal daydream—equal parts magic, nature, and melancholy.”
I assume this is useful for something more important than Tik Tok posts but I’m not sure what. Still, damned impressive. And addictive.